© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20062
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States in a geopolitical context

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States and its government or military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.65
     lockout
    -0.64
     sublime
    -0.63
    rawdownloadcloneembedreportprint
    -0.63
     description
    -0.62
     clutch
    -0.61
     brill
    -0.61
    rower
    -0.61
     catalogue
    -0.60
    mble
    -0.58
    POSITIVE LOGITS
    annie
    0.75
    ĺ
    0.73
    pol
    0.73
    polit
    0.72
    «
    0.72
     Airlines
    0.70
     policymakers
    0.70
    Americans
    0.70
    aturdays
    0.70
     lawmakers
    0.67
    Activations Density 0.289%

    No Known Activations